Systems and methods for data analysis

Abstract

The present disclosure provides systems and methods for data analysis. An example method may comprise receiving a data stream comprising a plurality of records. A record of said plurality of records may comprise a plurality of attributes. The method may further comprise classifying each of said plurality of attributes as a dimension or a measure. The method may further comprise dividing said plurality of records into a plurality of time periods. The method may further comprise, for a time period of said plurality of time periods, generating one or more segments of records. Each segment of the one or more segments may comprise records having a combination of dimensions with unique values as compared to other segments of said one or more segments. The method may further comprise applying an algorithm to said one or more segments to generate an output. The method may further comprise displaying, on a graphical user interface, a graphical representation of said output to a user.

What is claimed is: 
     
       1. A method, comprising:
 a) receiving a data stream comprising a plurality of records, wherein a record of said plurality of records comprises a plurality of attributes, wherein said plurality of attributes comprises at least one dimension and at least one measure; 
 b) classifying each of said plurality of attributes as a dimension or a measure; 
 c) generating a summary of a measure in said plurality of records; 
 d) dividing said plurality of records into a plurality of time periods; 
 e) generating a summary of a measure in records in a time period of said plurality of time periods; 
 f) for a time period of said plurality of time periods, generating one or more segments of records, wherein each segment of said one or more segments comprises records having a combination of dimensions with unique values as compared to other segments of said one or more segments; 
 g) discarding segments that contain less than a threshold quantity of records or summary value; 
 h) applying an algorithm to said one or more segments to generate an output; and 
 i) displaying, on a graphical user interface, a graphical representation of said output to a user. 
 
     
     
       2. The method of  claim 1 , wherein said dimensions are qualitative attributes. 
     
     
       3. The method of  claim 1 , wherein said measures are quantitative attributes. 
     
     
       4. The method of  claim 1 , wherein said summary comprises one or more of a sum, mean, median, and mode of said measure across said plurality of records. 
     
     
       5. The method of  claim 1 , wherein said summary comprises one or more of a sum, mean, median, and mode of said measure across said records in said time period. 
     
     
       6. The method of  claim 1 , wherein a quantity of said plurality of time periods is bounded. 
     
     
       7. The method of  claim 1 , wherein said one or more segments generated in (f) comprise every possible combination of dimensions. 
     
     
       8. The method of  claim 1 , wherein a quantity of said one or more segments is bounded. 
     
     
       9. The method of  claim 1 , wherein said one or more segments are generated after a single pass through said data stream. 
     
     
       10. The method of  claim 1 , wherein said one or more segments are generated after a second pass through said data stream. 
     
     
       11. The method of  claim 1 , wherein said output indicates whether a measure in a selected segment of said one or more segments is an outlier as compared to said measure in other segments of said one or more segments. 
     
     
       12. The method of  claim 1 , wherein said output comprises a forecast of one or more measures in at least one segment of said one or more segments for at least one time period of said plurality of time periods. 
     
     
       13. The method of  claim 12 , further comprising comparing said forecast to actual values of said one or more measures in said at least one segment of said one or more segments for said at least one time period of said plurality of time periods, and identifying one or more outlier segments for each of said one or more measures based at least in part on said comparison of said forecast to said actual values. 
     
     
       14. The method of  claim 1 , wherein said output indicates whether a first segment of said one or more segments is correlated with a second segment of said one or more segments. 
     
     
       15. The method of  claim 1 , wherein said output ranks one or more measures in each of said one or more segments based at least in part on relevance to each of said one or more segments. 
     
     
       16. The method of  claim 1 , wherein (f) is performed for each time period of said plurality of time periods. 
     
     
       17. The method of  claim 13 , wherein said output indicates whether a segment in a first time period of said plurality of time periods is correlated with a corresponding segment in a second time period of said plurality of time periods.